Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design

• URL: http://arxiv.org/abs/2603.00152v2
• Date: Thu, 05 Mar 2026 15:40:26 GMT
• Title: Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design
• Authors: Haoxiang Sun, Tao Wang, Chenwei Tang, Li Yuan, Jiancheng Lv,
• Abstract summary: We propose Dr.Seg, a simple, plug-and-play GRPO-based framework consisting of a Look-to-Confirm mechanism and a Distribution-Ranked Reward module.<n>Experiments demonstrate that Dr.Seg improves performance in complex visual scenarios while maintaining strong generalization.
• Score: 39.867923322793246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLMs) for visual perception tasks (e.g., detection and segmentation). However, much of this line of research rests on a long-standing yet unexamined assumption: training paradigms developed for language reasoning can be transferred seamlessly to visual perception. Our experiments show that this assumption is not valid, revealing intrinsic differences between reasoning-oriented and perception-oriented settings. Using reasoning segmentation as a representative case, we surface two overlooked factors: (i) the need for a broader output space, and (ii) the importance of fine-grained, stable rewards. Building on these observations, we propose Dr.~Seg, a simple, plug-and-play GRPO-based framework consisting of a Look-to-Confirm mechanism and a Distribution-Ranked Reward module, requiring no architectural modifications and integrating seamlessly with existing GRPO-based VLLMs. Extensive experiments demonstrate that Dr.~Seg improves performance in complex visual scenarios while maintaining strong generalization. Code, models, and datasets are available at https://github.com/eVI-group-SCU/Dr-Seg.

Related papers

• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? [50.92401586025528]
  Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear.<n>We introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks.
  arXiv  Detail & Related papers  (2026-03-03T18:36:16Z)
• Understanding the Transfer Limits of Vision Foundation Models [38.99867932557529]
  Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks.<n>We postulate that this limitation arises from a mismatch between pretraining objectives and the demands of downstream vision-and-imaging tasks.<n>Pretraining strategies like masked image reconstruction or contrastive learning shape representations for tasks such as recovery of generic visual patterns or global semantic structures.<n>Our findings indicate that better alignment between pretraining and downstream tasks, measured by simple divergence metrics such as maximum-mean-discrepancy (MMD) between the same features before and after fine-tuning, correlates with greater performance improvements and
  arXiv  Detail & Related papers  (2026-01-22T12:07:56Z)
• DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model [22.28268642142352]
  DiG (Differential Grounding) is a novel proxy task framework where MLLMs learn fine-grained perception by identifying and localizing all differences between similar image pairs without prior knowledge of their number.<n>Our results highlight differential grounding as a scalable and robust approach for advancing fine-grained visual reasoning in MLLMs.
  arXiv  Detail & Related papers  (2025-12-14T10:40:27Z)
• ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection [51.93101033997245]
  Increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations.<n>We propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection.<n>We show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark.
  arXiv  Detail & Related papers  (2025-09-24T07:34:09Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning [0.42855555838080844]
  This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought prompting and reinforcement learning.<n>We find that simple CoT formats, where the model generates a reasoning step before the answer, can harm the model's original performance.<n>In contrast, structured multi-stage prompting based on scene graphs (SceneGraph CoT) significantly improves spatial reasoning accuracy.
  arXiv  Detail & Related papers  (2025-07-06T10:51:12Z)
• Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme [36.34443944082215]
  This work introduces a transparent, from-scratch framework forReinforcement learning (RL) in vision-based models (VLMs)<n>It offers a minimal yet functional four-step pipeline validated across multiple models and datasets.<n>In addition, a standardized evaluation scheme is proposed to assess training dynamics and reflective behaviors.
  arXiv  Detail & Related papers  (2025-04-03T13:53:28Z)
• OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles [91.88062410741833]
  We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning.<n>We show that OpenVLThinker-7B consistently advances performance across six benchmarks demanding mathematical and general reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning [62.61187785810336]
  ImageScope is a training-free, three-stage framework that unifies language-guided image retrieval tasks.<n>In the first stage, we improve the robustness of the framework by synthesizing search intents across varying levels of semantic granularity.<n>In the second and third stages, we reflect on retrieval results by verifying predicate propositions locally, and performing pairwise evaluations globally.
  arXiv  Detail & Related papers  (2025-03-13T08:43:24Z)
• AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO [0.0]
  Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring visual spatial reasoning.<n>We introduce a novel two-stage training framework designed to equip standard LLMs with visual reasoning abilities for maze navigation.
  arXiv  Detail & Related papers  (2025-02-20T16:05:18Z)
• GiT: Towards Generalist Vision Transformer through Universal Language Interface [94.33443158125186]
  This paper proposes a simple, yet effective framework, called GiT, simultaneously applicable for various vision tasks only with a vanilla ViT. GiT is a multi-task visual model, jointly trained across five representative benchmarks without task-specific fine-tuning.
  arXiv  Detail & Related papers  (2024-03-14T13:47:41Z)
• Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations [70.41385310930846]
  We present an end-to-end framework Structure-CLIP to enhance multi-modal structured representations. We use scene graphs to guide the construction of semantic negative examples, which results in an increased emphasis on learning structured representations. A Knowledge-Enhance (KEE) is proposed to leverage SGK as input to further enhance structured representations.
  arXiv  Detail & Related papers  (2023-05-06T03:57:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.